Remove unused data and add fixes (#5154)

* Remove unused data and add fixes

* Add missing file

* Address review comments

* Replace the scope of vq allocation

7 files changed, 3 insertions, 6 deletions

diff --git a/common/sampling.cpp b/common/sampling.cpp
index efd7eab6..e8675a8c 100644
--- a/common/sampling.cpp
+++ b/common/sampling.cpp
@@ -13,6 +13,7 @@ struct llama_sampling_context * llama_sampling_init(const struct llama_sampling_
         // will be empty (default) if there are parse errors
         if (result->parsed_grammar.rules.empty()) {
             fprintf(stderr, "%s: failed to parse grammar\n", __func__);
+            delete result;
             return nullptr;
         }
 
diff --git a/examples/infill/infill.cpp b/examples/infill/infill.cpp
index 4a782787..72fb133b 100644
--- a/examples/infill/infill.cpp
+++ b/examples/infill/infill.cpp
@@ -241,7 +241,7 @@ int main(int argc, char ** argv) {
     LOG("add_bos: %d\n", add_bos);
 
     bool suff_rm_leading_spc = params.escape;
-    if (suff_rm_leading_spc && params.input_suffix.find_first_of(" ") == 0 && params.input_suffix.size() > 1) {
+    if (suff_rm_leading_spc && params.input_suffix.find_first_of(' ') == 0 && params.input_suffix.size() > 1) {
         params.input_suffix.erase(0, 1);
         suff_rm_leading_spc = false;
     }
diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
index 4a0338a3..f2cd86af 100644
--- a/examples/llava/clip.cpp
+++ b/examples/llava/clip.cpp
@@ -1277,7 +1277,6 @@ bool clip_model_quantize(const char * fname_inp, const char * fname_out, const i
         ".*weight",
     };
 
-    std::vector<uint8_t> read_data(512);
     std::vector<uint8_t> work(512);
     std::vector<float> conv_buf(512);
     std::vector<int64_t> hist_all(1 << 4, 0);
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index af63f2f6..f58a2aca 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -681,7 +681,7 @@ struct llama_server_context
                     while ((pos = prompt.find(pattern, pos)) != std::string::npos) {
                         size_t end_prefix = pos;
                         pos += pattern.length();
-                        size_t end_pos = prompt.find("]", pos);
+                        size_t end_pos = prompt.find(']', pos);
                         if (end_pos != std::string::npos)
                         {
                             std::string image_id = prompt.substr(pos, end_pos - pos);
diff --git a/pocs/vdot/vdot.cpp b/pocs/vdot/vdot.cpp
index e96372c4..73ffcd1c 100644
--- a/pocs/vdot/vdot.cpp
+++ b/pocs/vdot/vdot.cpp
@@ -243,7 +243,6 @@ int main(int argc, char** argv) {
     if (useQ4_1) q41.resize(n4);
     else q40.resize(n4);
     std::vector<block_q8_0> q8(n8);
-    std::vector<int64_t> H(16, 0);
     double sumt = 0, sumt2 = 0, maxt = 0;
     double sumqt = 0, sumqt2 = 0, maxqt = 0;
     double sum = 0, sumq = 0, exactSum = 0;
diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp
index 55ce14e0..e3c656f5 100644
--- a/tests/test-backend-ops.cpp
+++ b/tests/test-backend-ops.cpp
@@ -102,7 +102,6 @@ static std::vector<float> tensor_to_float(const ggml_tensor * t) {
                     } else if (t->type == GGML_TYPE_I8) {
                         tv.push_back((float)*(int8_t *) &buf[i]);
                     } else if (quantized) {
-                        std::vector<float> vq(ggml_blck_size(t->type));
                         tt.to_float(&buf[i], vq.data(), ggml_blck_size(t->type));
                         tv.insert(tv.end(), vq.begin(), vq.end());
                     } else {
diff --git a/tests/test-llama-grammar.cpp b/tests/test-llama-grammar.cpp
index 73dd33dd..78fc4111 100644
--- a/tests/test-llama-grammar.cpp
+++ b/tests/test-llama-grammar.cpp
@@ -190,7 +190,6 @@ int main()
         index++;
     }
 
-    std::vector<std::vector<const llama_grammar_element *>> next_stacks;
     std::vector<llama_grammar_candidate> next_candidates;
     next_candidates.resize(24);